Recent Advances in Deep Learning (AI602, Spring 2021)

Deep learning is a new area of machine learning research, which have demonstrated states-of-the-art performance on many artificial intelligence tasks, e.g., computer vision, speech recognition and natural language processing. In this lecture, I will cover some of recent advances (made mostly in the last 5 years) in this area.

Announcement

• The maximum number of course registrations is around 80, and we cannot accept more now (do not send an email to Instructor or TA).

• Office hours: Every Monday, 12pm-2pm, N1-914

• Paper presentation schedule: Please refer to the KLMS notice.

Schedule

• Lecture 0: Introduction to AI602

• Lecture 1: Advanced optimizers for neural networks

• Lecture 2: Advanced deep spatial models (e.g., for image recognition)

• Lecture 3: Advanced deep temporal models (e.g., for language modeling)

• Lecture 4: Advanced deep generative models I (e.g., for image generation)

• Lecture 5: Advanced deep generative models II (e.g., for density estimation)

• Lecture 6: Novelty and uncertainty estimation

• Lecture 7: Unsupervised and self-supervised representation learning

• Lecture 8: Transfer and continual learning

• Lecture 9: Network compression

• Lecture 10: Few-shot learning

• Lecture 11: Adversarial robustness

• Lecture 12: Interpretable and explainable learning

Contact

Instructor: Jinwoo Shin (jinwoos@kaist.ac.kr)
TAs: Hyuntak Cha (hyuntak.cha@kaist.ac.kr), Junsu Kim (junsu.kim@kaist.ac.kr), Seunghyun Lee (seunghyun.lee@kaist.ac.kr), Sumin Shin (sym807@kaist.ac.kr) and Jihoon Tack (jihoontack@kaist.ac.kr)